English(EN) Prime Intellect has released prime-rl 0.6.0, an open framework for training trillion-parameter Mixture-of-Experts models on agentic reinforcement learning workl

Prime Intellect 发布用于训练万亿参数 MoE 模型的开放框架

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-23 07:53

Prime Intellect 推出了 prime-rl 0.6.0，一个用于使用 agentic 强化学习训练大型专家混合 (MoE) 模型的开放框架。该新系统成功在软件工程任务上训练了 GLM-5 模型，仅使用 28 个 H200 GPU 实现了 131k 的序列长度。 AI

影响能够更有效地训练大规模 AI 模型，可能加速 agentic 强化学习领域的研究。

排序理由发布用于训练大型 AI 模型的开源框架。 [lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发布用于训练大型 AI 模型的开源框架。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 110 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-06-23 07:53

Prime Intellect发布prime-rl 0.6.0，一个用于在agentic强化学习工作中训练万亿参数Mixture-of-Experts模型的开放框架

Prime Intellect has released prime-rl 0.6.0, an open framework for training trillion-parameter Mixture-of-Experts models on agentic reinforcement learning workloads. The system trained GLM-5 on software engineering tasks at 131k sequence length using just 28 H200 GPUs. https://ww…

本文如何被排名

报道来源 [1]

Prime Intellect发布prime-rl 0.6.0，一个用于在agentic强化学习工作中训练万亿参数Mixture-of-Experts模型的开放框架

相关实体

相关话题